• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.3C
• /
• pp.115-125
• /
• 2009

The preconsolidation pressure has been commonly determined by oedometer test. However, it can also be determined by insitu test, such as piezocone test with theoretical and(or) empirical correlations. Recently, Neural Network (NN) theory was applied and some models were proposed to estimate the preconsolidation pressure or OCR. It was already found that NN model can come over the site dependency and prediction accuracy is greatly improved when compared with present theoretical and empirical models. However, since the optimization process of synaptic weights of NN model is dependent on the initial synaptic weights, NN models which are trained with different initial weights can't avoid the variability on prediction result for new database even though they have same structure and use same transfer function. In this study, Committee Neural Network (CNN) model is proposed to improve the initial weight dependency of multi-layered neural network model on the prediction of preconsolidation pressure of soft clay from piezocone test result. Prediction results of CNN model are compared with those of conventional empirical and theoretical models and multi-layered neural network model, which has the optimized structure. It was found that even though the NN model has the optimized structure for given training data set, it still has the initial weight dependency, while the proposed CNN model can improve the initial weight dependency of the NN model and provide a consistent and precise inference result than existing NN models.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.3
• /
• pp.238-244
• /
• 2008

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing. This paper presents gamma neural network(GAM) to improve the dynamics of multilayer network. The GAM network uses the gamma memory kernel in the hidden layer of feedforword multilayer network. The GAM network is evaluated in linear and nonlinear system identification, and compared with feedforword(FNN) and recurrent neural networks(RNN) for the relative comparison of its performance. Experimental results show that the GAM network performs better with respect to the convergence and accuracy, indicating that it can be a more effective network than conventional multilayer networks in system identification.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.3C
• /
• pp.271-278
• /
• 2003

In this paper, we propose a new MLP based detector which has low circuit complexity and fast adaptation capability for CDMA downlink in frequency selective fading, and is easy for parameter optimization. The simplified structure of the proposed MLP is designed by making use of transmission characteristics of downlinks such that all users signals transmitted over same propagation paths and the number of channelization codes are limited. Significant performance improvement over Rake receiver can be obtained with the proposed MLP and the efficiency of the proposed MLP was compared with that of conventional MLP.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.6
• /
• pp.585-591
• /
• 2002

While the multilayer perceptron(MLP) provides several advantages against the existing pattern recognition methods, it requires relatively long time in learning. This results in prolonging speaker enrollment time with a speaker verification system that uses the MLP as a classifier. This paper proposes a method that shortens the enrollment time through adopting the cohort speakers method used in the existing parametric systems and reducing the number of background speakers required to learn the MLP, and confirms the effect of the method by showing the result of an experiment that applies the method to a continuant and MLP-based speaker verification system.

• The KIPS Transactions:PartB
• /
• v.8B no.4
• /
• pp.327-334
• /
• 2001

본 논문에서는 기울기하강과 동적터널링이 조합된 학습알고리즘의 다층신경망을 이용한 고신회성의 회귀분석 모델을 제안하였다. 기울기하강은 빠른 수렴속도의 최적화가 가능하도록 하기 위함이고, 동적터널링은 국소최적해를 만났을 때 이를 벗어난 새로운 연결가중치를 설정하여 전역최적해로 수렴되도록 하기 위함이다. 또한 대용량의 입력 데이터를 통계적으로 독립인 특징들의 집합으로 변환시키는 주요성분분석 기법의 속성을 살려 학습데이터의 차원을 감소시킴으로서 고차원의 학습데이터에 따른 회귀분석 모델의 제약도 동시에 해결하였다. 제안된 기법의 신경망을 3개의 독립변수 패턴을 가진 암모니아 제조공정문제와 10개의 독립변수 패턴을 가진 자동차 연비문제에 각각 적용하여 시뮬레이션한 결과, 기존의 역전과 알고리즘의 신경망이나 주요성분분석에 의한 차원을 감소시키지 않은 학습패턴을 이용한 신경망보다 각각 더욱 우수한 학습성능과 회귀성능이 있음을 확인할 수 있었다. 또한 학습패턴의 영평균 정규화로 회귀용 신경망의 성능을 더욱 더 개선하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.19-20
• /
• 2017

인공지능이 사회적으로 대두되면서 많은 양의 관련 연구가 시작되고 있다. 본 논문에서는 다층 퍼셉트론 신경망에서 역전파 학습의 진행 과정을 시각화 하는 것을 목표로 하고 있다. 다층 퍼셉트론 신경망은 학습의 진행 과정과 그 방식은 잘 알려져 있으나 각 신경의 값이 어떻게 변화되어 가는 지는 눈에 보이지 않는다. 이러한 과정에 대해 시각화를 통해 값이 변하는 과정을 눈으로 쉽게 관찰할 수 있도록 하는 것이 이 논문의 목표이다. 본 연구결과는 향후 다층 퍼셉트론 신경망을 기반으로 하는 다른 모델의 시각화에 대한 기초자료로 활용될 수 있을 것이다.

• Information and Communications Magazine
• /
• v.33 no.10
• /
• pp.40-48
• /
• 2016

본고에서는 최근 활발하게 연구되고 있는 심층 학습에 대하여 알아본다. 기계 학습 분야 중 하나인 심층 학습은 인공 신경망의 한 형태인 심층 신경망을 통해 구현된다. 심층 신경망은 기존 다층 신경망의 구조와 거의 유사한 학습 구조를 가지지만, 학습 과정에서 발생하는 부정확한 학습 문제를 해결함으로써 최근의 성공을 이끌어낼 수 있었다. 본고에서는 다층 신경망이 가지고 있던 문제점들을 심층 신경망에서 어떻게 극복하였는지 심층 신경망의 발전 과정을 통해 알아보고, 기계 학습의 기본개념을 바탕으로 이를 설명하여 비전문가들의 이해를 돕고자 하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.360-366
• /
• 2003

Although multilayer perceptrons (MLPs) present several advantages against other pattern recognition methods, MLP-based speaker verification systems suffer from slow enrollment speed caused by many background speakers to achieve a low verification error. To solve this problem, the quantitative discriminative cohort speakers (QnDCS) method, by introducing the cohort speakers method into the systems, reduced the number of background speakers required to enroll speakers. Although the QnDCS achieved the goal to some extent, the improvement rate for the enrolling speed was still unsatisfactory. To improve the enrolling speed, this paper proposes the qualitative DCS (QlDCS) by introducing a qualitative criterion to select less background speakers. An experiment for both methods is conducted to use the speaker verification system based on MLPs and continuants, and speech database. The results of the experiment show that the proposed QlDCS method enrolls speakers in two times shorter time than the QnDCS does over the online error backpropagation(EBP) method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.2
• /
• pp.53-59
• /
• 2006

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing such as system identification and signal prediction. This paper proposes the gamma neural network(GAM), which uses gamma memory kernel in the hidden layer of feedforward multilayered network, to improve dynamics of networks and then describes nonlinear adaptive prediction using the proposed network as an adaptive filter. The proposed network is evaluated in nonlinear signal prediction and compared with feedforword(FNN) and recurrent neural networks(RNN) for the relative comparison of prediction performance. Simulation results show that the GAM network performs better with respect to the convergence speed and prediction accuracy, indicating that it can be a more effective prediction model than conventional multilayered networks in nonlinear prediction for nonstationary signals.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.233-236
• /
• 2000

본 연구에서는 패턴 인식용 다층 퍼셉트론 신경망을 순수 디지털 논리회로 모델로 전환 구현할 수 있도록 새로운 논리뉴런의 구조, 디지털 정형 다층논리신경망 구조, 그리고 패턴인식의 응용을 위한 다단 다층논리 신경망 구조를 제안하고, 또한 제안된 구조는 매우 단순하면서도 효과적인 증가적인 가법적(Incremental Additive) 학습알고리즘이 존재함을 보였다.